Engine valve clearance diagnostics based on vibration signals and machine learning methods

Internal combustion engines are commonly applied in vehicles and stationary equipment. They convert the energy contained in the fuel into mechanical work of the rotating crankshaft and, like all mechanical equipment, are subject to wear and tear and aging. The engine durability is described with design properties and, to a great extent, depends on the conditions of operation and the nature of the loads. As the engine degradation processes advance (variable temperatures, tribological processes, cavitation, chemical and electrochemical corrosion, aging etc.) the reliability and efficiency parameters deteriorate. As a consequence, the object wears, fails or is withdrawn from operation for economic or environmental reasons. Ever since the beginning of combustion engines, it has been observed that one of the key problems having impact on the engine operation is its correct adjustment. Degradation of the engine structure and engine incorrect adjustment may lead to the following phenomena in the internal combustion engine: deterioration of the engine efficiency, reduction of power, related to the reduction of mechanical efficiency, thermal efficiency and filling coefficient, increase in the emission of toxic compounds in the exhaust fumes, and possible damage to the engine components. Fig. 1a presents the differences in the fuel consumption for different valve clearance adjustments, and Fig. 1b presents the changes in the impact velocities of the valve against the valve seat allowing for the cam lift h). From the data shown in Fig. 1a, it follows that the changes in the valve clearance may lead to increased fuel consumption by the investigated internal combustion engine by approx. 9%, while the analysis of Fig. 1b leads to a conclusion that with the increasing valve clearance (lines: blue and green Fig.1b), the velocity of the impact of the valve against the valve seat grows, causing additional unwanted dynamic loads on the engine cylinder head of the engine. There are many methods of diagnosing the technical condition of combustion engines. They can be divided into methods utilizing Table 3. Steady state availability versus for Case 2

[1]  Stephanos Theodossiades,et al.  On the identification of piston slap events in internal combustion engines using tribodynamic analysis , 2015 .

[2]  Yaguo Lei,et al.  Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization , 2018, Mechanical Systems and Signal Processing.

[3]  Chi-Man Vong,et al.  Sparse Bayesian extreme learning committee machine for engine simultaneous fault diagnosis , 2016, Neurocomputing.

[4]  F. Gao,et al.  Fault Diagnosis for Engine Based on Single-Stage Extreme Learning Machine , 2016 .

[5]  Zhenyuan Zhong,et al.  Fault diagnosis for diesel valve trains based on time–frequency images , 2008 .

[6]  Edvard Govekar,et al.  Semi-supervised vibration-based classification and condition monitoring of compressors , 2017 .

[7]  AYYASAMY KRISHNAMOORTHY BABU,et al.  MISFIRE DETECTION IN A MULTI-CYLINDER DIESEL ENGINE : A MACHINE LEARNING APPROACH , 2016 .

[8]  Grenville J. Armitage,et al.  A survey of techniques for internet traffic classification using machine learning , 2008, IEEE Communications Surveys & Tutorials.

[9]  Marco Cocconcelli,et al.  Anomaly detection in a cutting tool by k-means clustering and support vector machines , 2017 .

[10]  Robert B. Randall,et al.  Model-based diagnosis of large diesel engines based on angular speed variations of the crankshaft , 2010 .

[11]  Jian-Da Wu,et al.  An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network , 2009, Expert Syst. Appl..

[12]  S. Arundathi.  Data Mining: A prediction for Student's Performance Using Decision Tree ID3 Method , 2014 .

[13]  Andrew Ball,et al.  On acoustic measurement-based condition monitoring of internal combustion engines , 2008 .

[14]  M. Muñoz,et al.  Diagnostic method based on the analysis of the vibration and acoustic emission energy for emergency diesel generators in nuclear plants , 2013 .

[15]  Amit Shrestha,et al.  Detection of Combustion Resonance Using an Ion Current Sensor in Diesel Engines , 2011 .

[16]  Cai Lei,et al.  Fault diagnosis for diesel valve trains based on non-negative matrix factorization and neural network ensemble , 2009 .

[17]  Liangpei Zhang,et al.  A Nonlocal Weighted Joint Sparse Representation Classification Method for Hyperspectral Imagery , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[18]  Bogusław Łazarz,et al.  Condition monitoring of engine timing system by using wavelet packet decomposition of a acoustic signal , 2014 .

[19]  Hans Bodén,et al.  Comparison of different methods to couple nonlinear source descriptions in the time domain to linear system descriptions in the frequency domain- : Application to a simple valveless one-cylinder cold engine , 2006 .

[20]  C. Özkan,et al.  Comparison of maximum likelihood classification method with supervised artificial neural network algorithms for land use activities , 2004 .

[21]  L. K. Hansen,et al.  On condition monitoring of exhaust valves in marine diesel engines , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[22]  Mark Senldge,et al.  Piezoelectric Accelerometers and Vibration Preamplifiers , 2011 .

[23]  Chris K. Mechefske,et al.  Fault detection and diagnosis in low speed rolling element bearings Part II: The use of nearest neighbour classification , 1992 .

[24]  R. Liebich,et al.  Impact detection using a machine learning approach and experimental road roughness classification , 2019, Mechanical Systems and Signal Processing.

[25]  Francesc Pozo,et al.  Wind turbine fault detection and classification by means of image texture analysis , 2018, Mechanical Systems and Signal Processing.

[26]  Franciszek Tomaszewski,et al.  Diagnostics of automatic compensators of valve clearance in combustion engine with the use of vibration signal , 2016 .

[27]  M. Destain,et al.  Defect segmentation on 'Jonagold' apples using colour vision and a Bayesian classification method , 1999 .

[28]  Yaguo Lei,et al.  Application of an intelligent classification method to mechanical fault diagnosis , 2009, Expert Syst. Appl..

[29]  Piotr Czech,et al.  DIAGNOSING OF CAR ENGINE FUEL INJECTORS DAMAGE USING DWT ANALYSIS AND PNN NEURAL NETWORKS , 2013 .